© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 3040
    Prev
    Next
    INDEX
    Explanations

    figur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lighter
    -0.08
     �
    -0.07
     لتح
    -0.07
    throws
    -0.07
    へ
    -0.07
    lights
    -0.07
    verb
    -0.07
    Grouping
    -0.07
    lecture
    -0.07
     Noel
    -0.07
    POSITIVE LOGITS
     khusus
    0.08
     gør
    0.08
    /classes
    0.08
     Serious
    0.08
     hardcore
    0.08
     fatty
    0.08
     gis
    0.07
     Als
    0.07
     sif
    0.07
     stated
    0.07
    Activations Density 0.002%

    No Known Activations